To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation
Abstract
Reordering poses a major challenge in machine translation (MT) between two languages with significant differences in word order. In this paper, we present a novel reordering approach utilizing sparse features based on dependency word pairs. Each instance of these features captures whether two words, which are related by a dependency link in the source sentence dependency parse tree, follow the same order or are swapped in the translation output. Experiments on Chinese-to-English translation show a statistically significant improvement of 1.21 BLEU point using our approach, compared to a state-of-the-art statistical MT system that incorporates prior reordering approaches.
Cite
Text
Hadiwinoto et al. "To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation." AAAI Conference on Artificial Intelligence, 2016. doi:10.1609/AAAI.V30I1.10386Markdown
[Hadiwinoto et al. "To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation." AAAI Conference on Artificial Intelligence, 2016.](https://mlanthology.org/aaai/2016/hadiwinoto2016aaai-swap/) doi:10.1609/AAAI.V30I1.10386BibTeX
@inproceedings{hadiwinoto2016aaai-swap,
title = {{To Swap or Not to Swap? Exploiting Dependency Word Pairs for Reordering in Statistical Machine Translation}},
author = {Hadiwinoto, Christian and Liu, Yang and Ng, Hwee Tou},
booktitle = {AAAI Conference on Artificial Intelligence},
year = {2016},
pages = {2943-2949},
doi = {10.1609/AAAI.V30I1.10386},
url = {https://mlanthology.org/aaai/2016/hadiwinoto2016aaai-swap/}
}